[Executor]CUDAGraph support Speculate Decode (#3769)

* success run ngram

* Revert "[Code Simplification] remove cum_offsets (#3410)"

This reverts commit 32b39620bc.

* success run ngram5 tp4 42bs

* success run ngram5 tp4 42bs

* mtp draft commit

* add decorator for target model

* enable draft model in cudagraph v0.5

* revert revrt cum_offset

* enable target model in cudagraph v0.9 And clean debug code

* Revert "success run ngram"

This reverts commit 8351e83993.

* add reverted code

* enable target model in cudagraph v0.9

* solve comment

* fix bid < 0

* Enable Target Model Padding And Draft Model in cudagraph

* solve problem

* delete rebuild padding debug note

* fast compile

* Add capture list for mtp

* success run 256 tp1 mtp

* Enable Lite TP2 Bsz256

* realy enable tp2 bsz 256

* fix problem

* Solve problem for Draft model in cudagraph

* Solve comment

* replace emptytensor as zeros

* Solve comments

* Revert "fast compile"

This reverts commit 834639a7ff.

* fix bug

* fix merge bug

* fix typo

* fix bug

---------

Co-authored-by: lizexu <2694294196@qq.com>
Co-authored-by: littledgg <1658565283@qq.com>
Co-authored-by: zeroRains <linjunlu@zerorains.top>
Co-authored-by: gongshaotian <gstain5555@outlook.com>

custom_ops/gpu_ops/cpp_extensions.cc

@@ -684,7 +684,7 @@ void SpeculateVerify(
     const paddle::Tensor &output_cum_offsets,
     const paddle::Tensor &actual_candidate_len,
     const paddle::Tensor &actual_draft_token_nums, const paddle::Tensor &topp,
-    int max_seq_len, int verify_window, bool enable_topp, bool benchmark_mode);
+    int max_seq_len, int verify_window, bool enable_topp, bool benchmark_mode, bool accept_all_drafts);
 
 void SpeculateUpdate(const paddle::Tensor &seq_lens_encoder,
                        const paddle::Tensor &seq_lens_decoder,